Seminar Schedule



MSCS 310

Dr. Adam Molnar
OSU Dept of Statistics

Mathematics and Success in STAT 2013

Every semester, hundreds of students enroll in Stat 2013, and every semester, many students do not successfully complete the course. Motivated by a state mandate to offer statistics without a college algebra prerequisite, we began an analysis of Stat 2013 students' mathematics ability and the relationship between mathematics skill and statistics success. Students from seven Spring 2019 sections participated in the analysis. Two tasks commenced:

1) Develop a valid open-resource mathematics diagnostic that evaluates students on mathematical topics used in introductory statistics. Reliability and factor analysis were used.

2) Investigate the association between course grade and student factors such as GPA, math test score, transfer status, and hours worked for pay. Multivariate models were built for binary success (ABC grade vs DFW grade), ordinal letter grade, and numeric course percentage.

This talk will summarize progress made and lessons learned, both quantitative and qualitative.



LSE 103

Dr. Pratyaydipta Rudra
OSU Department of Statistics

Bayesian networks in integrative genomics: An example with a recombinant inbred mouse panel



MSCS 310

Dr. Andy Luse
OSU Department of Management Science and Information Systems


MSCS 310

Dr. Bing Yao
OSU Department of Industrial Engineering and Management

Physical-statistical Modeling and Optimization of Complex Systems – Healthcare and Manufacturing Applications


Advanced sensing provides unprecedented opportunities for data-driven modeling, monitoring, and control of complex systems. Realizing full potentials of sensing data depends greatly on novel analytical methods for system informatics and decision making. My research objective is to integrate physics-based principles with statistical models to create enabling methodologies for optimal decision making in complex systems. In this talk, I will present two topics that tackle the data science challenges in healthcare and manufacturing. First, a physics-driven spatiotemporal regularization method is developed for high-dimensional predictive modeling to investigate heart electrical activity. This model not only captures the physics-based interrelationship between the dynamic variables, but also addresses the spatial and temporal regularizations to improve the prediction performance. Second, I will present a sequential framework to optimize the additive manufacturing (AM) process. This framework integrates the sensor-based modeling of defect states with Markov decision process to sequentially optimize the AM build quality.

About the speaker:

Bing Yao is currently an assistant professor in the School of Industrial Engineering and Management at Oklahoma State University. She received her PhD degree in Industrial Engineering and Operations Research from the Pennsylvania State University. Her research focuses on developing interdisciplinary data-driven models for decision optimization in complex systems. This research has broad applications in both advanced manufacturing and healthcare.



MSCS 310

Dr. Barney Luttbeg
OSU Department of Integrative Biology


MSCS 310

Dr. Michael Higgins
Department of Statistics
Kansas State University




MSCS 310


Carol Powers Ph.D.
Coordinator of Graduate Professional Development
OSU Graduate College

“360o Critical Skills for Career Success”

Come learn more about professional development programming at OSU. The Graduate College hosts the 360° Critical Skills for Career Success micro-credential program to help graduate students develop transferrable skills that will help differentiate them in the job market and be successful in their chosen career.

Refreshments immediately following seminar in Room 309 MSCS.



MSCS 310

Dr Chenang Liu
OSU Department of Industrial Engineering and Management

Smart Additive Manufacturing Using Advanced Data Analytics

Abstract: One of the major concerns in additive manufacturing (AM, also known as 3D printing) is to ensure product quality and consistency, and enable its sustainability. To address this issue, the objective of this research is to develop methodologies that are able to online diagnose and further improve the AM process, i.e., to build a basis for smart additive manufacturing. To achieve this goal, novel advanced data analytics approaches with effective online sensing platforms were developed. The effectiveness of the proposed methodologies was demonstrated using both numerical simulations and actual AM case studies.